HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

DeepScaleR-1.5B-Preview-unsloth-bnb-4bit

unsloth/DeepScaleR-1.5B-Preview-unsloth-bnb-4bit

kind
bnb-4bit
quant
4bit
family
misc
modality
text-generation
root model
agentica-org/DeepScaleR-1.5B-Preview
provider
unsloth
license
mit
language
en
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
153
likes
0
created
—
last modified
2025-02-15T22:52:09+00:00 (2025)
huggingface
https://huggingface.co/unsloth/DeepScaleR-1.5B-Preview-unsloth-bnb-4bit
tags
transformerssafetensorsqwen2text-generationdeepseekunslothqwenconversationalenbase_model:agentica-org/DeepScaleR-1.5B-Previewbase_model:quantized:agentica-org/DeepScaleR-1.5B-Previewlicense:mittext-generation-inferenceendpoints_compatible4-bitbitsandbytesregion:us

Benchmark scores (5)

benchmarkcategoryscorecontextconfevidence
MATH-500math79.8low| 2.5-7B-Instruct | 13.3 | 79.8 | 50.6 | 34.6 | 40.7 | 43.8 |
Math Olympiadmath40.7low| 2.5-7B-Instruct | 13.3 | 79.8 | 50.6 | 34.6 | 40.7 | 43.8 |
MATHmath34.6low| 2.5-7B-Instruct | 13.3 | 79.8 | 50.6 | 34.6 | 40.7 | 43.8 |
MATHmath26.7rStar-Math-7Bmedium| rStar-Math-7B | 26.7 | 78.4 | 47.5 | - | 47.1 | - |
AIME 2024math13.3low| 2.5-7B-Instruct | 13.3 | 79.8 | 50.6 | 34.6 | 40.7 | 43.8 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.